Update app.py

app.py

@@ -18,4 +18,5 @@ if text:
     input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
     output_ids = model.generate(input_ids.to('cuda'))
     response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
-    print(response)
+    print(response)
+    st.json(response)